Edit model card

Saiga_timelist_task100steps

This model is a fine-tuned version of TheBloke/Llama-2-7B-fp16 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.7978

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-06
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 5
  • total_train_batch_size: 10
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 100

Training results

Training Loss Epoch Step Validation Loss
No log 0.13 10 1.7979
1.6502 0.26 20 1.7978
1.6502 0.39 30 1.7978
1.675 0.52 40 1.7978
1.675 0.64 50 1.7978
1.7226 0.77 60 1.7978
1.7226 0.9 70 1.7978
1.6832 1.03 80 1.7977
1.6832 1.16 90 1.7979
1.6793 1.29 100 1.7978

Framework versions

  • PEFT 0.10.0
  • Transformers 4.39.3
  • Pytorch 2.2.2+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
4
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for marcus2000/Saiga_timelist_task100steps

Adapter
(14)
this model